Is Stochastic Gradient Descent Near Optimal?

Yifan Zhu Hong Jun Jeon Benjamin Van Roy

Published in: CoRR (2022)

Keyphrases

stochastic gradient descent
loss function
least squares
step size
matrix factorization
random forests
weight vector
multiple kernel learning
online algorithms
support vector machine
importance sampling
cost function
regularization parameter
online learning
pairwise
decision trees
feature vectors